Joe / @joedaroo:

An OpenAI agent security executive on being surprised by “staggering” model capabilities, AI labs needing a “culture of reasonable paranoia”, and more  —  Took a minute to write a few words about security & safety as someone who lived through it all at OpenAI. I hope my thoughts help someone out there. https://x.com/...

Joe / @joedaroo:

An OpenAI agent security executive on being surprised by “staggering” model capabilities, AI labs needing a “culture of reasonable paranoia”, and more  —  Took a minute to write a few words about security & safety as someone who lived through it all at OpenAI. I hope my thoughts help someone out there. https://x.com/...

Source: TechMeme
Source Link: https://www.techmeme.com/260928/p25#a260928p25